© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3289
    Prev
    Next
    INDEX
    Explanations

    then followed by verbs or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inoltre
    -0.07
     ëĺIJíķľ
    -0.07
     infatti
    -0.07
    話ãģĮ
    -0.07
    inya
    -0.07
    miss
    -0.07
    åIJŀåIJIJ
    -0.07
    ves
    -0.07
    æľĢç»Ī
    -0.07
     totiž
    -0.07
    POSITIVE LOGITS
    æł¹æį®éľĢè¦ģ
    0.10
    /OR
    0.09
    çĶ±åİŁåijĬ
    0.08
    ä»ĸéĤ£
    0.08
    åĥıä½ł
    0.08
     others
    0.08
    ãģĿãĤĮãĤĴ
    0.07
    suming
    0.07
     optionally
    0.07
    gether
    0.07
    Activations Density 0.044%

    No Known Activations